{"id":"https://openalex.org/W4389272742","doi":"https://doi.org/10.1142/s2717554523500248","title":"Finetuning Pretrained Model with Embedding of Domain and Language Information for ASR of Very Low-Resource Settings","display_name":"Finetuning Pretrained Model with Embedding of Domain and Language Information for ASR of Very Low-Resource Settings","publication_year":2023,"publication_date":"2023-12-01","ids":{"openalex":"https://openalex.org/W4389272742","doi":"https://doi.org/10.1142/s2717554523500248"},"language":"en","primary_location":{"id":"doi:10.1142/s2717554523500248","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2717554523500248","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2433/286875","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015958922","display_name":"Kak Soky","orcid":"https://orcid.org/0000-0002-7014-147X"},"institutions":[{"id":"https://openalex.org/I186365177","display_name":"Institute of Technology of Cambodia","ror":"https://ror.org/054z67s11","country_code":"KH","type":"education","lineage":["https://openalex.org/I186365177"]}],"countries":["KH"],"is_corresponding":true,"raw_author_name":"Kak Soky","raw_affiliation_strings":["Cambodia Academy of Digital Technology (CADT), Bridge 2, National Road 6A, Sangkat Prek Leap, Khan Chroy Changva, Phnom Penh, Cambodia"],"raw_orcid":"https://orcid.org/0000-0002-7014-147X","affiliations":[{"raw_affiliation_string":"Cambodia Academy of Digital Technology (CADT), Bridge 2, National Road 6A, Sangkat Prek Leap, Khan Chroy Changva, Phnom Penh, Cambodia","institution_ids":["https://openalex.org/I186365177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology, Soraku-gun, Kyoto 619-0289, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7636-3797","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Soraku-gun, Kyoto 619-0289, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102757632","display_name":"Chenhui Chu","orcid":"https://orcid.org/0000-0001-9848-6384"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenhui Chu","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9848-6384","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2686-2296","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015958922"],"corresponding_institution_ids":["https://openalex.org/I186365177"],"apc_list":null,"apc_paid":null,"fwci":0.1586,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55487957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"33","issue":"04","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.665074348449707},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6552541255950928},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5872056484222412},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5512604713439941},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5227032899856567},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4254688620567322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3875506818294525},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32131463289260864},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07342937588691711},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.04688912630081177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.665074348449707},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6552541255950928},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5872056484222412},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5512604713439941},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5227032899856567},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4254688620567322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3875506818294525},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32131463289260864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07342937588691711},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.04688912630081177},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1142/s2717554523500248","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2717554523500248","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01221:0006026386","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/286875","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50728049","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100930624","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01221:0006026386","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/286875","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal article"},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2363020693","display_name":"A Study on Multi-modal Automatic Simultaneous Interpretation System and Evaluation Method","funder_award_id":"21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G832091749","display_name":"\u610f\u56f3\u3092\u7684\u78ba\u306b\u4f1d\u3048\u308b\u97f3\u58f0\u5bfe\u8a71\u7ffb\u8a33\u306e\u57fa\u76e4\u6280\u8853\u306e\u5275\u51fa","funder_award_id":"23K28144","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8471687183","display_name":"M3OLR: Towards Effective Multilingual, Multimodal and Multitask Oriental Low-resourced Language Speech Recognition","funder_award_id":"23K11227","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2510867321","https://openalex.org/W2796339975","https://openalex.org/W2826003142","https://openalex.org/W2889374926","https://openalex.org/W2936774411","https://openalex.org/W2939164678","https://openalex.org/W2964243145","https://openalex.org/W2979826702","https://openalex.org/W3007550212","https://openalex.org/W3097643313","https://openalex.org/W3097777922","https://openalex.org/W3097904285","https://openalex.org/W3122931219","https://openalex.org/W3143843080","https://openalex.org/W3155427814","https://openalex.org/W3180180466","https://openalex.org/W3196419581","https://openalex.org/W3198429080","https://openalex.org/W3198528147","https://openalex.org/W3202370288","https://openalex.org/W3211278025","https://openalex.org/W3213029956","https://openalex.org/W4205900877","https://openalex.org/W4286498414","https://openalex.org/W4296069120","https://openalex.org/W4297841331","https://openalex.org/W4372271612"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2951819827","https://openalex.org/W2849310602","https://openalex.org/W2419146053","https://openalex.org/W2088247287","https://openalex.org/W3006008237","https://openalex.org/W2963903416"],"abstract_inverted_index":{"This":[0],"study":[1],"investigates":[2],"the":[3,62,106,127,151,154,158,162,169,173,177,197,222,229],"effective":[4],"incorporation":[5],"of":[6,70,126,153,161,172,179,233],"meta-information":[7,198],"such":[8],"as":[9],"domain":[10,95,112,137,146,215],"and":[11,96,119,142,217],"language":[12,93,121,129,140,143,219],"in":[13,28,92,176,182,199],"finetuning":[14,109],"a":[15,55,67,208],"pretrained":[16,33],"model":[17],"based":[18],"on":[19],"self-supervised":[20],"learning":[21,99,103],"(SSL)":[22],"for":[23,139,145],"automatic":[24],"speech":[25],"recognition":[26],"(ASR)":[27],"very":[29],"low-resource":[30],"settings.":[31],"SSL":[32],"models":[34],"have":[35],"been":[36],"shown":[37],"to":[38,45,76,83,188],"achieve":[39,77],"comparable":[40],"or":[41,94,101,201],"even":[42,49],"better":[43],"performance":[44],"conventional":[46],"end-to-end":[47],"systems":[48],"when":[50],"we":[51,81],"finetune":[52],"them":[53],"with":[54,66],"small":[56],"dataset.":[57],"However,":[58],"it":[59],"still":[60],"requires":[61],"specific":[63],"target":[64,166,230],"dataset":[65,167,232],"considerable":[68],"amount":[69],"labeled":[71,231],"data,":[72],"like":[73],"10":[74,189],"h,":[75],"satisfactory":[78],"performance.":[79,241],"Thus,":[80],"propose":[82],"exploit":[84],"heterogeneous":[85],"datasets":[86,125],"which":[87,114,123,212],"are":[88],"partially":[89],"matched":[90],"either":[91],"apply":[97],"multi-task":[98],"(MTL)":[100],"adversarial":[102],"(ADV)":[104],"using":[105],"meta-information.":[107],"The":[108,133,165,191],"comprises":[110],"(1)":[111],"adaptation,":[113,122],"uses":[115,124],"in-domain":[116],"multi-lingual":[117],"datasets,":[118],"(2)":[120],"same":[128],"but":[130],"different":[131],"domains.":[132],"auxiliary":[134,155],"task":[135,156],"is":[136,168,221],"identification":[138,144],"adaptation":[141,210,216,220],"adaptation.":[147],"We":[148,225],"then":[149,218],"embed":[150],"output":[152,160],"into":[157],"encoder":[159],"ASR":[163,205],"task.":[164],"Khmer":[170],"corpus":[171],"Extraordinary":[174],"Chambers":[175],"Courts":[178],"Cambodia":[180],"(ECCC)":[181],"various":[183],"sizes":[184],"from":[185],"one":[186],"hour":[187],"h.":[190],"experimental":[192],"evaluations":[193],"demonstrate":[194],"that":[195,228],"fusing":[196],"MTL":[200],"ADV":[202],"significantly":[203],"improves":[204],"accuracy.":[206],"Moreover,":[207],"two-step":[209],"method":[211],"first":[213],"conducts":[214],"most":[223],"effective.":[224],"also":[226],"show":[227],"only":[234],"5":[235],"h":[236],"gives":[237],"an":[238],"almost":[239],"saturated":[240]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}